Class AssociateGreedyDesc<D>

Type Parameters:
D - Feature description type.

public class AssociateGreedyDesc<D> extends AssociateGreedyDescBase<D>

Brute force greedy association for objects described by a TupleDesc_F64. An object is associated with whichever object has the best fit score and every possible combination is examined. If there are a large number of features this can be quite slow.

Optionally, backwards validation can be used to reduce the number of false associations. Backwards validation works by checking to see if two objects are mutually the best association for each other. First an association is found from src to dst, then the best fit in dst is associated with feature in src.

  • Constructor Details

    • AssociateGreedyDesc

      public AssociateGreedyDesc(ScoreAssociation<D> score)
      Configure association
      Parameters:
      score - Computes the association score.
  • Method Details